Serve as a senior technical authority responsible for designing and delivering advanced AI and cloud platform architectures using Red Hat OpenShift, Red Hat AI Inference Server, OpenShift AI, and hybrid/multi-cloud environments. Enable on-prem model training, enterprise-grade inference, and automation-driven managed service platforms. Drive deep technical exploration, feasibility assessments, and end-to-end implementation patterns that position the organization as a next-gen AI-driven managed services provider.
Key Responsibilities:
- Architect robust platforms leveraging Red Hat OpenShift, Red Hat AI Inference Server (vLLM-based), OpenShift AI, and associated Red Hat AI products.
- Design and implement AI inference and on-prem model training solutions using vLLM, KServe/ModelMesh, llm-d, GPU orchestration, and Red Hat's validated model catalog.
- Build hybrid and multi-cloud AI platforms across on-prem OpenShift, OpenShift on AWS (ROSA), and other hyperscaler environments.
- Lead identification, exploration, and implementation of AI/LLM use cases that leverage Red Hat inference and training capabilities.
- Develop cloud-agnostic architectures enabling distributed inference, model serving, GPU scaling, and seamless workload placement across clouds.
- Own and deliver PoCs, performance benchmarks, and architectural accelerators that validate solution feasibility.
- Implement automation using Ansible, Terraform, GitOps, and OpenShift-native tooling to standardize multi-cluster operations.
- Establish best practices for observability, cost optimization, governance, and platform security for AI workloads.
- Work with cybersecurity teams to incorporate zero-trust, threat detection, and compliance principles into platform blueprints.
- Serve as a senior technical mentor, guiding engineering teams in deep technical problem-solving, architectural simplification, and design reviews.
- Create reusable architecture patterns, operators, templates, and deployment assets that scale across hybrid/multi-cloud environments.
- Participate in technical governance, architectural due diligence, and customer facing solution architecture discussions.
Required Skills & Experience:
- Hands-on mastery of Red Hat OpenShift (4.x) including cluster architecture, operators, GitOps, networking, service mesh, and lifecycle automation.
- Strong experience with Red Hat AI Inference Server, vLLM-based model hosting, GPU workloads, and performance tuning.
- Solid knowledge of OpenShift AI (KServe, ModelMesh, GPU placement, distributed inference).
- Proven experience designing architectures spanning on-prem, ROSA/AWS, Azure/ARO, or GCP.
- Strong proficiency in Linux (RHEL), Kubernetes internals, container runtimes, and cloud networking.
- Advanced automation skills using Ansible, Terraform, and GitOps workflows.
- Exposure to on-prem model training, GPU-accelerated pipelines, and edge or regulated workloads.
- Familiarity with platform observability, monitoring stacks, FinOps, and governance frameworks
Preferred / Good-to-Have
- Experience with distributed inference frameworks (e.g., llm-d).
- Understanding of RAG workflows, Llama Stack APIs, or enterprise agentic architectures.
- Security background in SOC, SIEM, or threat intelligence platforms.
- Red Hat certifications (RHCA / OpenShift / RHEL / Ansible)
- Experience in customer-facing architecture or technical consulting roles.
Soft Skills
- Deep problem-solving capability with strong architectural communication.
- Ability to work as a senior IC guiding multiple engineering streams.
- Comfortable with ambiguity, exploratory work, and rapid prototyping.
- Strong technical influencing skills across teams and customer stakeholders.
